A Convolutional Neural Network Combining Discriminative Dictionary Learning and Sequence Tracking for Left Ventricular Detection

Abstract

Cardiac MRI left ventricular (LV) detection is frequently employed to assist cardiac registration or segmentation in computer-aided diagnosis of heart diseases. Focusing on the challenging problems in LV detection, such as the large span and varying size of LV areas in MRI, as well as the heterogeneous myocardial and blood pool parts in LV areas, a convolutional neural network (CNN) detection method combining discriminative dictionary learning and sequence tracking is proposed in this paper. To efficiently represent the different sub-objects in LV area, the method deploys discriminant dictionary to classify the superpixel oversegmented regions, then the target LV region is constructed by label merging and multi-scale adaptive anchors are generated in the target region for handling the varying sizes. Combining with non-differential anchors in regional proposal network, the left ventricle object is localized by the CNN based regression and classification strategy. In order to solve the problem of slow classification speed of discriminative dictionary, a fast generation module of left ventricular scale adaptive anchors based on sequence tracking is also proposed on the same individual. The method and its variants were tested on the heart atlas data set. Experimental results verified the effectiveness of the proposed method and according to some evaluation indicators, it obtained 92.95% in AP50 metric and it was the most competitive result compared to typical related methods. The combination of discriminative dictionary learning and scale adaptive anchor improves adaptability of the proposed algorithm to the varying left ventricular areas. This study would be beneficial in some cardiac image processing such as region-of-interest cropping and left ventricle volume measurement.

Detection of Left Ventricular Cavity from Cardiac MRI Images Using Faster R-CNN

“…There are a limited number of methods for the automatic detection of cardiac objects, for instance, model-based [8][9][10], machine learning [11], and deep learning models [12][13][14]. Due to some reasons, such as inhomogeneous intensity, diversities in the size and shape of LV at different slices, and an insignificant intensity difference between LV and surrounding tissues, the accurate localization of LV from MRI images is critical.…”

“…Among these methods, Faster R-CNN was preferred since it surpassed other methods in speed and accuracy [20]. Wang et al [14] also determined that LV detection currently relies on two-phase methods, and Faster R-CNN demonstrated the most outstanding performances. However, its ability to directly detect the LV from cardiac MRI images is still limited.…”

“…Various CNN-based detection methods have been proposed to overcome these issues and were shown to perform well. As explained by Wang et al [14], these approaches can be classified as one-phase, two-phase, and anchor-free. YOLO [17] and SSD [18] are one-phase detection techniques aiming to direct classification and regression to the sliding windows.…”

“…Due to the scarcity of medical MRI data, training deeper networks, which require large amounts of data in order to reach high accuracy, becomes problematic. According to Wang et al [14], in one-stage and anchor-free detection techniques, the network seems to be a black box with difficulty in detecting objects directly from input images. Thus, based on the preceding restrictions, LV detection is mostly depends on twostage approaches.…”

Automatic Identification of Bioprostheses on X-ray Angiographic Sequences of Transcatheter Aortic Valve Implantation Procedures Using Deep Learning

“…This automatic detection points directly to the hot topic of Artificial Intelligence (AI) in medical imaging [ 9 ]. AI has been successfully applied to several cardiovascular imaging modalities [ 10 , 11 ]; however, its use in percutaneous cardiovascular interventions has scarcely been reported [ 12 ].…”